© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 15186
    Prev
    Next
    INDEX
    Explanations

    phrases indicating focus on a specific concept or topic

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "this"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¹ãĥĪ
    -0.97
     è£ıè¦ļéĨĴ
    -0.74
    omo
    -0.70
    ãĥĭ
    -0.68
    ãĥı
    -0.68
    ivas
    -0.67
    Īè
    -0.67
    ielding
    -0.67
    berman
    -0.66
    umer
    -0.66
    POSITIVE LOGITS
     week
    0.88
     guy
    0.87
     trope
    0.83
     madness
    0.81
     morning
    0.79
     incarnation
    0.78
     sucker
    0.77
     kind
    0.77
     weekend
    0.77
     installment
    0.76
    Activations Density 0.310%

    No Known Activations